Add optional use_effective_order parameter to BLEU score #1862
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original BLEU fails at answers shorter than four tokens, since the amount of 4-grams is zero. Adding the use effective order parameter allows the user to still obtain scores considering only n-grams up to the amount of tokens in the answer when N<4.
dosubot
bot
added
the
size:XS
|
Hey @JonasElburgUVA thanks for taking notice. There was a slight mistake in your implementation so I have changed, you may use it like from ragas.dataset_schema import SingleTurnSample
from ragas.metrics import BleuScore
sample = SingleTurnSample(
response="The Eiffel Tower is located in India.",
reference="The Eiffel Tower is located in Paris."
)
scorer = BleuScore(kwargs={"use_effective_order":True})
await scorer.single_turn_ascore(sample)``` |
shahules786
approved these changes
Jan 21, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
The original BLEU score fails for answers shorter than four tokens because the number of 4-grams is zero. Adding the use_effective_order parameter allows users to obtain scores by considering only n-grams up to the number of tokens in the answer when ( N < 4 ). This feature is already implemented in sacreBLEU, so we only need to add the parameter to the BLEU object in ragas. The default is set to False to maintain previous behavior.